Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 74 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.9774. Min Act: -0.1700

Data Index: 1432594 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.8837. Min Act: -0.1700

Data Index: 801184 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.8524. Min Act: -0.1700

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.8524. Min Act: -0.1700

Data Index: 960552 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.7587. Min Act: -0.1700

Data Index: 1031689 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.8212. Min Act: -0.1700

Data Index: 837617 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.8212. Min Act: -0.1700

Data Index: 1548240 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.7587. Min Act: -0.1700

Data Index: 1405735 (Python Code)

Max Activating Token Index: 975

Text #8

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6649. Min Act: -0.1700

Data Index: 1630882 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6337. Min Act: -0.1700

Data Index: 1520313 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6337. Min Act: -0.1700

Data Index: 1636545 (Python Code)

Max Activating Token Index: 975

Text #11

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6337. Min Act: -0.1700

Data Index: 1384110 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6649. Min Act: -0.1700

Data Index: 1602872 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6962. Min Act: -0.1700

Data Index: 1396339 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6962. Min Act: -0.1700

Data Index: 1340998 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6024. Min Act: -0.1700

Data Index: 566314 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6962. Min Act: -0.1700

Data Index: 1389885 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1379461 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1080168 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 5.9774. Min Range: -5.9774

Max Act: 5.6337. Min Act: -0.1700

Data Index: 317564 (C4 (Web Text))

Max Activating Token Index: 223